Function quantize_caffe_model

ppq/api/interface.py:349–450

量化一个 caffe 原生的模型 输入一个 caffe 模型的文件路径和权重路径 返回一个量化后的 PPQ.IR.BaseGraph quantize caffe model, input caffe prototxt and weight path, return a quantized ppq graph Args: caffe_proto_file (str): 被量化的 caffe 模型文件 .prototxt 路径

(
    caffe_proto_file: str,
    caffe_model_file: str,
    calib_dataloader: DataLoader,
    calib_steps: int,
    input_shape: List[int],
    platform: TargetPlatform,
    input_dtype: torch.dtype = torch.float,
    setting: QuantizationSetting = None,
    collate_fn: Callable = None,
    inputs: List[Any] = None,
    do_quantize: bool = True,
    device: str = 'cuda',
    verbose: int = 0,
)

@ empty_ppq_cache
def quantize_caffe_model(
    caffe_proto_file: str,
    caffe_model_file: str,
    calib_dataloader: DataLoader,
    calib_steps: int,
    input_shape: List[int],
    platform: TargetPlatform,
    input_dtype: torch.dtype = torch.float,
    setting: QuantizationSetting = None,
    collate_fn: Callable = None,
    inputs: List[Any] = None,
    do_quantize: bool = True,
    device: str = 'cuda',
    verbose: int = 0,
) -> BaseGraph:
    """
        量化一个 caffe 原生的模型
            输入一个 caffe 模型的文件路径和权重路径
            返回一个量化后的 PPQ.IR.BaseGraph
        quantize caffe model, input caffe prototxt and weight path, return a quantized ppq graph
    Args:
        caffe_proto_file (str): 被量化的 caffe 模型文件 .prototxt 路径
                                caffe prototxt location

        caffe_model_file (str): 被量化的 caffe 模型文件 .caffemodel 路径
                                caffe weight location

        calib_dataloader (DataLoader): 校准数据集 calibration data loader

        calib_steps (int): 校准步数 calibration steps

        collate_fn (Callable): 校准数据的预处理函数 batch collate func for preprocessing

        input_shape (List[int]): 模型输入尺寸，用于执行 jit.trace，对于动态尺寸的模型，输入一个模型可接受的尺寸即可。
            如果模型存在多个输入，则需要使用 inputs 变量进行传参，此项设置为 None
                                a list of ints indicating size of input, for multiple inputs, please use
                                keyword arg inputs for direct parameter passing and this should be set to None

        input_dtype (torch.dtype): 模型输入数据类型，如果模型存在多个输入，则需要使用 inputs 变量进行传参，此项设置为 None
                                the torch datatype of input, for multiple inputs, please use keyword arg inputs
                                for direct parameter passing and this should be set to None

        setting (OptimSetting): 量化配置信息，用于配置量化的各项参数，设置为 None 时加载默认参数。
                                Quantization setting, default setting will be used when set None

        inputs (List[Any], optional): 对于存在多个输入的模型，在Inputs中直接指定一个输入List，从而完成模型的tracing。
                                for multiple inputs, please give the specified inputs directly in the form of
                                a list of arrays

        do_quantize (Bool, optional): 是否执行量化 whether to quantize the model, defaults to True, defaults to True.

        platform (TargetPlatform, optional): 量化的目标平台 target backend platform, defaults to TargetPlatform.DSP_INT8.

        device (str, optional): 量化过程的执行设备 execution device, defaults to 'cuda'.

        verbose (int, optional): 是否打印详细信息 whether to print details, defaults to 0.

    Raises: